Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling

by   K. Darshana Abeyrathna, et al.

Using logical clauses to represent patterns, Tsetlin machines (TMs) have recently obtained competitive performance in terms of accuracy, memory footprint, energy, and learning speed on several benchmarks. A team of Tsetlin automata (TAs) composes each clause, thus driving the entire learning process. These are rewarded/penalized according to three local rules that optimize global behaviour. Each clause votes for or against a particular class, with classification resolved using a majority vote. In the parallel and asynchronous architecture that we propose here, every clause runs in its own thread for massive parallelism. For each training example, we keep track of the class votes obtained from the clauses in local voting tallies. The local voting tallies allow us to detach the processing of each clause from the rest of the clauses, supporting decentralized learning. Thus, rather than processing training examples one-by-one as in the original TM, the clauses access the training examples simultaneously, updating themselves and the local voting tallies in parallel. There is no synchronization among the clause threads, apart from atomic adds to the local voting tallies. Operating asynchronously, each team of TA will most of the time operate on partially calculated or outdated voting tallies. However, across diverse learning tasks, it turns out that our decentralized TM learning algorithm copes well with working on outdated data, resulting in no significant loss in learning accuracy. Further, we show that the approach provides up to 50 times faster learning. Finally, learning time is almost constant for reasonable clause amounts. For sufficiently large clause numbers, computation time increases approximately proportionally. Our parallel and asynchronous architecture thus allows processing of more massive datasets and operating with more clauses for higher accuracy.


page 1

page 2

page 3

page 4


Coalesced Multi-Output Tsetlin Machines with Clause Sharing

Using finite-state machines to learn patterns, Tsetlin machines (TMs) ha...

Asynchronous Decentralized Parallel Stochastic Gradient Descent

Recent work shows that decentralized parallel stochastic gradient decent...

Asynchronous Decentralized Learning of a Neural Network

In this work, we exploit an asynchronous computing framework namely ARoc...

Tell Me Something New: a new framework for asynchronous parallel learning

We present a novel approach for parallel computation in the context of m...

Fast Processing of Large Graph Applications Using Asynchronous Architecture

Graph algorithms and techniques are increasingly being used in scientifi...

Learning Without a Global Clock: Asynchronous Learning in a Physics-Driven Learning Network

In a neuron network, synapses update individually using local informatio...

Improving Efficiency in Large-Scale Decentralized Distributed Training

Decentralized Parallel SGD (D-PSGD) and its asynchronous variant Asynchr...